OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity
4,695 Commits 4 Branches 61 Tags 140 MiB
Commit Graph

4695 Commits

Author SHA1 Message Date
Davis King c0ab9a13d5 Added get_mapping_to_chip() 2014-09-02 20:47:33 -04:00
Davis King 0438ae5d03 Added an overload of render_face_detections() that takes just a single 
full_object_detection.
 2014-09-02 20:15:11 -04:00
Davis King 7b2839a9d9 Added methods to allow in-place modification of a full_object_detection. 2014-09-02 20:14:22 -04:00
Davis King 1ff7cd1ad7 Created release v18.10 2014-08-24 21:05:32 -04:00
Davis King cacfd0b4b2 Added tag v18.10 for changeset 5a14394843c0 2014-08-24 21:05:32 -04:00
Davis King 4da25bb4a0 updated docs 2014-08-24 21:02:43 -04:00
Davis King 0f6581a72d Fixed a minor bug. 2014-08-24 19:34:39 -04:00
Davis King 836a5392d2 updated release notes 2014-08-24 19:26:20 -04:00
Davis King c52484eba9 Fixed spelling error in comment 2014-08-24 19:20:42 -04:00
Davis King 2c0be3f995 changed cmake files a little to avoid warnings from the example programs. 2014-08-24 13:21:09 -04:00
Davis King 2ebafae736 added missing asserts 2014-08-24 12:43:51 -04:00
Davis King 1037b661a4 Added unit tests for the face processing code 2014-08-24 12:15:52 -04:00
Davis King 5e4aaf2e53 improved examples 2014-08-24 10:37:19 -04:00
Davis King 07541b4255 clarified docs 2014-08-24 09:01:41 -04:00
Davis King 687799f3f1 fleshed out the spec 2014-08-24 09:01:31 -04:00
Davis King 581af78978 updated docs 2014-08-23 23:33:00 -04:00
Davis King 946601ec2e updated docs 2014-08-23 21:24:01 -04:00
Davis King 954612b67c Cleaned up the code a bit. Still more cleaning to do. 2014-08-23 21:00:33 -04:00
Davis King b191400a00 Added initial version of shape training example 2014-08-21 22:42:48 -04:00
Davis King 5ae170c461 Added a face landmarking example program 2014-08-21 22:11:55 -04:00
Davis King c9f24f3da4 upped the imglab version number 2014-08-21 21:27:51 -04:00
Davis King e677b0570f Made the way the image_display draws parts not so awful. Now the parts 
will have a reasonable size based on the current zoom level.
 2014-08-21 21:07:45 -04:00
Davis King 1524020303 Added image shape prediction code. It works well, just need to fill out the 
spec and add asserts.
 2014-08-21 20:42:16 -04:00
Davis King 5de8793283 A minor change to avoid a compiler warning from gcc with -Wall is on. 2014-08-21 19:29:27 -04:00
Davis King adc4d68250 Made code work in C++03 and fixed a linker error 2014-08-21 19:16:49 -04:00
Davis King 878ded28ba Incorporated Changjiang Yang's patch that makes load_image() use the file 
headers to decide how to load images instead of using their file extensions.
This makes load_image() work even when the files have the incorrect file
extensions.
 2014-08-21 19:07:16 -04:00
Davis King 5a4f282348 Made the image views do range checking when asserts are enabled. 2014-08-19 21:00:26 -04:00
Davis King 320a48499b updated readme 2014-08-19 19:11:24 -04:00
Davis King 992175a6ee Fixed spelling error and clarified docs 2014-08-19 19:10:28 -04:00
Davis King 6b4d17e51e updated docs 2014-08-18 20:32:12 -04:00
Davis King 5ff02a2a2a Fixed the cmake files to avoid getting an error if the word cmake or various 
other words appear in the file path to the source code.
 2014-08-18 20:18:06 -04:00
Davis King 9069f30a6d minor code cleanup 2014-08-17 19:30:15 -04:00
Davis King 0b5cb827e2 Made the version of draw_line() that draws onto a regular image use alpha 
blending for drawing diagonal lines.
 2014-08-17 17:26:44 -04:00
Davis King 413096982b updated docs 2014-08-17 17:25:54 -04:00
Davis King 25a5455676 Added find_similarity_transform() 2014-08-16 12:47:07 -04:00
Davis King 3d9496d73d Renamed a variable to avoid a name conflict on windows which was pointed out by 
Ahti Leppänen.
 2014-08-15 20:16:21 -04:00
Davis King 55a0ee9c8d fixed typo in spec 2014-08-14 20:40:42 -04:00
Davis King e1887a24f7 Changed the evaluate_detectors() routine so that it applies non-max suppression 
to each detector individually.  This way one detector doesn't stomp on the
output of another detector.
 2014-08-13 19:06:26 -04:00
Davis King cd71dab3f2 Updated the Python API, train_simple_object_detector() so you can call it 
directly on already loaded data rather than needing to use an XML file as
input.
 2014-08-12 19:47:41 -04:00
Davis King ae9546cbdc Made svd3 faster when working on small matrices. 2014-08-11 19:51:05 -04:00
Davis King f9fac06e16 Made inv() handle singular matrices in a more reasonable way. Now it will make 
some effort to detect them and output an identity matrix in that case.
 2014-08-02 18:56:01 -04:00
Davis King f5c7248b20 Added assignment operator for scalar float assignments. 2014-07-24 21:38:26 -04:00
Davis King 679e75ae34 updated docs 2014-07-20 19:19:58 -04:00
Davis King aa1ccfcdfb clarified spec 2014-07-20 19:18:40 -04:00
Davis King 43f37209e3 Added links to the generic image definition in all the relevant abstract files. 2014-07-20 17:18:34 -04:00
Davis King a6dc296219 Fixed a bug where the imglab tool would sometimes start out with an annoyingly 
small window when the first image was bigger than the screen.
 2014-07-20 14:47:05 -04:00
Davis King 6d55fcc260 Made the disabled version of pyramid_down support the new image interface. 
Also added an overload of operator() for pyramid_down that takes just
a single image and downsamples it.
 2014-07-20 08:07:59 -04:00
Davis King 0eb725fc4f Clarified the exact size of the HOG feature maps produced by 
extract_fhog_features().  Also fixed a minor bug where empty planar HOG feature
maps had 0 planes in them rather than 31 empty planes as the spec says they
should.
 2014-07-19 12:09:55 -04:00
Davis King 98602c332a Fixed a color space handling bug in resize_image() 2014-07-18 22:44:11 -04:00
Davis King d75e747a1d Added a typedef to the object_detector that allows you to find out 
what scanner type it is using.
 2014-07-18 22:22:31 -04:00